tl-schema-org

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides utility scripts in Bash and PowerShell (scripts/update-schema-data.sh and scripts/update-schema-data.ps1) designed to fetch official Schema.org vocabulary files, including type and property CSVs, directly from the schema.org website. These downloads facilitate the skill's primary purpose of maintaining an up-to-date local reference for structured data modeling.
  • [INDIRECT_PROMPT_INJECTION]: The skill's architecture involves the ingestion of external data files which the agent is expected to process. * Ingestion points: Machine-readable files located in the assets/ directory (e.g., schemaorg-current-https-types.csv) are downloaded from external sources and intended to be parsed by the agent. * Boundary markers: There are no specific delimiters or instructional barriers provided to prevent the agent from potentially being influenced by malicious content embedded within the external CSV or JSON-LD files. * Capability inventory: The skill instructions encourage the agent to query these files to guide complex operations such as API design, database schema generation, and JSON-LD markup production. * Sanitization: The provided scripts and documentation do not include validation or sanitization routines for the content retrieved from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:03 AM